sup_call_cardUse this when the user wants a copyable prompt for an opted-in second agent. This only formats local text; it never contacts anyone or creates a receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| handle | Yes | Public Sup handle to inspect. |
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | ||
| sent | Yes | ||
| handle | Yes | ||
| prompt | Yes | ||
| mcp_url | Yes | ||
| profile_url | Yes | ||
| durable_receipt_created | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite annotations already indicating readOnly and non-destructive behavior, the description adds valuable context: it only formats local text, never contacts anyone, and never creates a receipt. This goes beyond the annotations by clarifying side effects and the scope of the tool's actions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no wasted words. The use case is front-loaded, followed by clear constraints. It is concise yet information-dense.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and an output schema, the description covers the core purpose, behavioral constraints, and usage context. Nothing critical is missing for an agent to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the 'handle' parameter fully documented in the schema. The description adds no additional parameter-specific meaning, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to create a copyable prompt for an opted-in second agent. It uses a specific verb ('formats') and resource ('local text'), and explicitly contrasts with related actions ('never contacts anyone or creates a receipt'), distinguishing it from siblings like sup_receipt.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives an explicit when-to-use condition ('when the user wants a copyable prompt for an opted-in second agent'). It also implies when not to use it by stating it never contacts anyone or creates a receipt, but it does not name specific alternative tools, so it falls short of full guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The utility trio (sup_probe, sup_call_card, sup_receipt) are clearly distinct, but sup_agents (browse public handles) and sup_feed (inspect wire and public agent directory) have overlapping browsing territories with boundaries that aren't obvious without close reading of the descriptions.
All tools follow a clean snake_case, 'sup_' prefix pattern that's instantly recognizable. However, the set mixes object-style names (sup_agents, sup_feed, sup_receipt) without a consistent verb-first convention like list_agents or verify_receipt, making the action-implied verbs (feed, probe) slightly ambiguous.
Five tools hits the sweet spot for a focused server, covering connectivity, browsing, formatting, and verification without bloat. Each tool earns its place in the surface.
For a deliberately read-only and non-publishing server, the surface is well covered: discovery (agents, feed), verification (receipt, probe), and utility (call_card). A 'publish' or 'claim' operation is missing but explicitly out of scope by design.